Re: [OMPI devel] v4.0.3rc3 ready for testing

[Geoffrey Paulsen via devel]

Thanks so much for testing.  If further testing reveals anything, please create an issue at https://github.com/open-mpi/ompi/.

---
Geoffrey Paulsen
Software Engineer, IBM Spectrum MPI
Email: gpaul...@us.ibm.com

 

 

----- Original message -----
From: "Heinz, Michael William" <michael.william.he...@intel.com>
To: Open MPI Developers <devel@lists.open-mpi.org>
Cc: Geoffrey Paulsen <gpaul...@us.ibm.com>
Subject: [EXTERNAL] RE: [OMPI devel] v4.0.3rc3 ready for testing
Date: Fri, Jan 31, 2020 11:36 AM
 

I’ve run the 3.1.6rc2 and 4.0.3rc3 src rpms through some smoke tests and they both built and ran properly on RHEL 8.

 

From: devel <devel-boun...@lists.open-mpi.org> On Behalf Of Geoffrey Paulsen via devel
Sent: Wednesday, January 29, 2020 7:03 PM
To: devel@lists.open-mpi.org
Cc: Geoffrey Paulsen <gpaul...@us.ibm.com>
Subject: [OMPI devel] v4.0.3rc3 ready for testing

 

Please test v4.0.3rc3:

   https://www.open-mpi.org/software/ompi/v4.0/

 

Changes since v4.0.2 include:

 

  4.0.3 -- January, 2020
  ------------------------

- Add support for Mellanox Connectx6.
- Fix a problem with Fortran compiler wrappers ignoring use of
  disable-wrapper-runpath configure option.  Thanks to David
  Shrader for reporting.
- Fixed an issue with trying to use mpirun on systems where neither
  ssh nor rsh is installed.
- Address some problems found when using XPMEM for intra-node message
  transport.
- Improve dimensions returned by MPI_Dims_create for certain
  cases.  Thanks to @aw32 for reporting.
- Fix an issue when sending messages larger than 4GB. Thanks to
  Philip Salzmann for reporting this issue.
- Add ability to specify alternative module file path using
  Open MPI's RPM spec file.  Thanks to @jschwartz-cray for reporting.
- Clarify use of --with-hwloc configuration option in the README.
  Thanks to Marcin Mielniczuk for raising this documentation issue.
- Fix an issue with shmem_atomic_set.  Thanks to Sameh Sharkawi for reporting.
- Fix a problem with MPI_Neighbor_alltoall(v,w) for cartesian communicators
  with cyclic boundary conditions.  Thanks to Ralph Rabenseifner and
  Tony Skjellum for reporting.
- Fix an issue using Open MPIO on 32 bit systems.  Thanks to
  Orion Poplawski for reporting.
- Fix an issue with NetCDF test deadlocking when using the vulcan
  Open MPIO component.  Thanks to Orion Poplawski for reporting.
- Fix an issue with the mpi_yield_when_idle parameter being ignored
  when set in the Open MPI MCA parameter configuration file.
  Thanks to @iassiour for reporting.
- Address an issue with Open MPIO when writing/reading more than 2GB
  in an operation.  Thanks to Richard Warren for reporting.

 

---
Geoffrey Paulsen
Software Engineer, IBM Spectrum MPI
Email: gpaul...@us.ibm.com